跳到正文
研踪PaperTrail
← 研踪 PaperTrail

arXiv:2605.19403 · v2

TIDE: Asymmetric Neural Circuits for Stabilized Temporal Inhibitory-Excitatory Dynamics

首次提交 2026-05-19 13:59
版本更新 2026-11-16 06:58
雷达观测 2026-11-17 17:12
arXiv ↗PDF ↗

摘要

Recent Continuous Thought Machine (CTM) architecture decouples internal computation from external inputs via neural dynamics, but relies on unconstrained multi-layer perceptrons for its recurrent computations. We propose to model neural dynamics using asymmetric Excitatory-Inhibitory (E-I) networks, which can be stabilized via principles from network theory, while obeying Dale's principle and can be expressed as energy-based systems optimized through a game-theoretic loss. Building on this perspective, we introduce Temporal Inhibitory-Excitatory Dynamic Engine (TIDE), a neuro-inspired architecture that computes internal representations through neural dynamics stabilized by incorporating the Wilson-Cowan dynamics and lateral inhibition. TIDE balances biological realism by, for instance, using Hierarchical Receptive Fields and enforcing Dale's principle to ensure a realistic 80:2080:20 E-I balance ratio with an end-to-end trainable architecture. The aim of this paper is to introduce a new architecture that brings neuro-inspired learning and architectural principles to the forefront. We present proofs of convergence, stability, and complexity bounds, along with empirical ablation studies. Overall, TIDE achieves higher top-1\texttt{top-1} accuracy than CTM on the majority of the investigated datasets while requiring a smaller training budget. Furthermore, across varying training budgets, TIDE improves top-1\texttt{top-1} accuracy on ImageNet-C by an average of +1.65+1.65% to +6.42+6.42% under different perturbation severity levels.

作者备注:Accepted in the 40th Conference on Neural Information Processing Systems [NeurIPS 2026]

AI 论文解读

基于摘要 · 非全文审阅

此版本尚未生成 AI 解读。解读由后台任务生成并按论文版本保存,登录后共享已有结果。

版本差异

本站首次收录为 v2,暂无更早版本可对照。

观测到的版本

相邻记录可能跳过中间版本;首次发现 v2 及以上也会标为版本更新。

v2 · 2026-11-16 06:58 · 最新观测版本

TIDE: Asymmetric Neural Circuits for Stabilized Temporal Inhibitory-Excitatory Dynamics

Recent Continuous Thought Machine (CTM) architecture decouples internal computation from external inputs via neural dynamics, but relies on unconstrained multi-layer perceptrons for its recurrent computations. We propose to model neural dynamics using asymmetric Excitatory-Inhibitory (E-I) networks, which can be stabilized via principles from network theory, while obeying Dale's principle and can be expressed as energy-based systems optimized through a game-theoretic loss. Building on this perspective, we introduce Temporal Inhibitory-Excitatory Dynamic Engine (TIDE), a neuro-inspired architecture that computes internal representations through neural dynamics stabilized by incorporating the Wilson-Cowan dynamics and lateral inhibition. TIDE balances biological realism by, for instance, using Hierarchical Receptive Fields and enforcing Dale's principle to ensure a realistic 80:2080:20 E-I balance ratio with an end-to-end trainable architecture. The aim of this paper is to introduce a new architecture that brings neuro-inspired learning and architectural principles to the forefront. We present proofs of convergence, stability, and complexity bounds, along with empirical ablation studies. Overall, TIDE achieves higher top-1\texttt{top-1} accuracy than CTM on the majority of the investigated datasets while requiring a smaller training budget. Furthermore, across varying training budgets, TIDE improves top-1\texttt{top-1} accuracy on ImageNet-C by an average of +1.65+1.65% to +6.42+6.42% under different perturbation severity levels.

查看此版本解读 →查看此版本原文 ↗